Related papers: SWE-World: Building Software Engineering Agents in…

Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks,…

With the advent of large language models (LLMs) in the artificial intelligence (AI) area, the field of software engineering (SE) has also witnessed a paradigm shift. These models, by leveraging the power of deep learning and massive amounts…

Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus…

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We find real-world software engineering to be a rich, sustainable, and…

As large language models (LLMs) evolve into sophisticated autonomous agents capable of complex software development tasks, evaluating their real-world capabilities becomes critical. While existing benchmarks like…

Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based…

Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising yet limited performance. However, most existing LLM agents…

This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…

Achieving spatial intelligence requires moving beyond visual plausibility to build world simulators grounded in physical laws. While coding LLMs have advanced static 3D scene generation, extending this paradigm to 4D dynamics remains a…

While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (for…

Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

Large language models generate plausible code but cannot verify correctness. Existing multi-agent systems simulate execution or leave verification optional. We introduce execution-grounded verification as a first-class principle: every code…

Large language models have demonstrated strong capabilities in individual software engineering tasks, yet most autonomous systems still treat issue resolution as a monolithic or pipeline-based process. In contrast, real-world software…

LLM agents excel in compact environments requiring deep reasoning but remain brittle when operating in broader, more complex contexts that demand robustness across diverse tools and schemas. Building bespoke environments for training is…

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development workflows. However, bridging the gap between static text-based…

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…